Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    plus or minus

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     jednocze
    -0.07
     archive
    -0.07
     EDUC
    -0.07
     Comprehensive
    -0.07
    颗
    -0.07
     hindsight
    -0.07
     IOCTL
    -0.07
    ஆ
    -0.07
    .Sample
    -0.07
    veau
    -0.06
    POSITIVE LOGITS
     /**<
    0.08
     PR
    0.08
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.07
    -Re
    0.07
    ,…
    0.07
     starring
    0.07
     ferr
    0.07
    ('${
    0.07
    燃气
    0.07
     (...)
    0.07
    Act Density 0.006%

    No Known Activations